
Senior AI Integration Engineer
Posted 6 days ago

Posted 6 days ago
This is a fully remote position, open to applicants in Colombia.
• Create high-performance, secure, and production-ready API layers.
• Design custom Model Context Protocol (MCP) servers.
• Execute real-time data delivery services tailored for human applications and autonomous AI agents.
• Function at high throughput — managing thousands of requests each second.
• Develop integration layers that AI agents depend on.
• **Must-Have**
• Overall Experience: 8+ years in Backend Software Engineering, Distributed Systems Architecture, or Enterprise Platform Engineering.
• Resiliency Engineering: 4+ years designing mission-critical systems that require "four-nines" (99.99%) availability, robust traffic shaping, and self-healing capabilities.
• AI & Agentic Systems: 2+ years creating production-grade integration layers, semantic context gateways, or RAG endpoints utilized by LLMs and autonomous AI agents.
• Expertise in Advanced API Design & Context Optimization.
• Production-level expertise in one or more of the following: C# (.NET Core), Java, Python, or Node.js/TypeScript.
• Proficiency in Enterprise Scalability & Traffic Management.
• Expertise in Lock & Contention Mitigation (API & Database Tier).
• Knowledge in Hardened Security, Governance & AI Isolation.
• **Preferred Experience**
• Experience with GraphQL and dynamic JSON/gRPC filtering layers (zero-waste data fetching).
• Development of custom MCP servers for LLM context exposure.
• Merging heterogeneous schemas for LLM tool-calling (e.g., relational databases, analytics platforms like Pendo/Hotjar, observability tools).
• Implementation of semantic token-aware API pagination and streaming.
• Creation of context-aware gateways for conditional object graph hydration based on agent intent.
• Edge performance experience: CloudFront Functions, Lambda@Edge, HTTP/3, WebSockets.
• Familiarity with PostgreSQL and OpenSearch/Elasticsearch access layers with sub-millisecond caching.
• Experience with reactive streams and rate-limiting for Amazon MSK (Kafka), SQS, and HTTP endpoints.
• Knowledge of Circuit Breakers, Bulkheads, and Retry-with-Exponential-Backoff (Polly, Resilience4j, or equivalent).
• Experience with Amazon MemoryDB / Redis OSS / Valkey for rate limiters, session caches, and semantic query caching.
• Implementation of Optimistic Concurrency Control (OCC) via eTags/versions; Pessimistic Locking only where absolutely necessary.
• Understanding of CQRS to separate high-volume writes from intensive read queries in PostgreSQL.
• Asynchronous write delegation for high-contention API writes to Kafka/MSK.
• Knowledge of Zero Trust security: OAuth2, OIDC, mTLS, and AWS Lake Formation.
• Experience with security proxy layers over Amazon Bedrock (prompt injection filtering, PII redaction, API token quota enforcement).
• Proficiency in end-to-end API runtime tracing with OpenTelemetry (oTel) and Datadog.
• Option for remote work.
• 13 floating holidays.
• 15 vacation days per year upon completion.
• Positive working environment.
NVIDIA
Towa Software
AIM Qualifications and Assessment Group
Get handpicked remote jobs straight to your inbox weekly.